Increasing power of Intel computer processor chips over years
Raw data Listing
Obs
CHIP
YEAR
TRANS
logTRANS
MIPS
1
4004
1971
2.3
0.8329
0.042
2
8008
1972
2.5
0.9163
0.045
3
8080
1974
4.5
1.5041
0.082
4
8086
1978
29.0
3.3673
0.527
5
80286
1982
134.0
4.8978
2.436
6
80386
1985
275.0
5.6168
5.000
7
80486
1989
1200.0
7.0901
21.818
8
Pentium (5)
1993
3100.0
8.0392
56.364
9
Pentium Pro (6)
1995
5500.0
8.6125
100.000
10
Pentium II
1997
7500.0
8.9227
136.364
11
Pentium III
1999
9500.0
9.1590
172.727
12
Pentium 4
2000
42000.0
10.6454
763.636
Data from Intel Corporation
Increasing power of Intel computer processor chips over years
Plot of the raw data
Plot of TRANS*YEAR. Legend: A = 1 obs, B = 2 obs, etc.
TRANS |
|
50000 +
|
|
|
|
|
| A
40000 +
|
|
|
|
|
|
30000 +
|
|
|
|
|
|
20000 +
|
|
|
|
|
|
10000 + A
|
| A
| A
|
| A
| A
0 + A A A A A A
|
---+-------------+-------------+-------------+-------------+-------------+-------------+--
1970 1975 1980 1985 1990 1995 2000
YEAR
Data from Intel Corporation
Increasing power of Intel computer processor chips over years
Plot of the log transformed data
Plot of logTRANS*YEAR. Legend: A = 1 obs, B = 2 obs, etc.
logTRANS |
|
12 +
|
|
|
| A
|
10 +
|
|
| A A
| A
|
8 + A
|
|
| A
|
|
6 +
| A
|
| A
|
|
4 +
|
| A
|
|
|
2 +
| A
|
| A
| A
|
0 +
|
---+-------------+-------------+-------------+-------------+-------------+-------------+--
1970 1975 1980 1985 1990 1995 2000
YEAR
Data from Intel Corporation
Increasing power of Intel computer processor chips over years
Computer Chip example using REG with CLM
The REG Procedure
Model: MODEL1
Dependent Variable: logTRANS
Number of Observations Read
12
Number of Observations Used
12
Analysis of Variance
Source
DF
Sum of Squares
Mean Square
F Value
Pr > F
Model
1
131.29985
131.29985
850.47
<.0001
Error
10
1.54386
0.15439
Corrected Total
11
132.84371
Root MSE
0.39292
R-Square
0.9884
Dependent Mean
5.80034
Adj R-Sq
0.9872
Coeff Var
6.77408
Parameter Estimates
Variable
DF
Parameter Estimate
Standard Error
t Value
Pr > |t|
95% Confidence Limits
Intercept
1
-632.78864
21.89772
-28.90
<.0001
-681.57980
-583.99749
YEAR
1
0.32150
0.01102
29.16
<.0001
0.29694
0.34607
Data from Intel Corporation
Increasing power of Intel computer processor chips over years
Computer Chip example using REG with CLM
The REG Procedure
Model: MODEL1
Dependent Variable: logTRANS
Output Statistics
Obs
YEAR
Dependent Variable
Predicted Value
Std Error Mean Predict
95% CL Mean
95% CL Predict
Residual
1
1971
0.8329
0.8974
0.2028
0.4455
1.3493
-0.0878
1.8826
-0.0645
2
1972
0.9163
1.2189
0.1938
0.7872
1.6506
0.2427
2.1950
-0.3026
3
1974
1.5041
1.8619
0.1764
1.4689
2.2549
0.9023
2.8215
-0.3578
4
1978
3.3673
3.1479
0.1454
2.8240
3.4719
2.2144
4.0814
0.2194
5
1982
4.8978
4.4339
0.1227
4.1605
4.7074
3.5168
5.3511
0.4639
6
1985
5.6168
5.3985
0.1143
5.1439
5.6530
4.4867
6.3102
0.2183
7
1989
7.0901
6.6845
0.1174
6.4229
6.9461
5.7707
7.5982
0.4056
8
1993
8.0392
7.9705
0.1357
7.6682
8.2728
7.0443
8.8967
0.0687
9
1995
8.6125
8.6135
0.1489
8.2817
8.9453
7.6773
9.5497
-0.001002
10
1997
8.9227
9.2565
0.1640
8.8910
9.6220
8.3078
10.2052
-0.3339
11
1999
9.1590
9.8995
0.1806
9.4971
10.3020
8.9360
10.8631
-0.7405
12
2000
10.6454
10.2210
0.1893
9.7992
10.6429
9.2492
11.1928
0.4244
Sum of Residuals
-5.6503E-13
Sum of Squared Residuals
1.54386
Predicted Residual SS (PRESS)
2.30901
Data from Intel Corporation
Increasing power of Intel computer processor chips over years
Computer Chip example using REG with CLM
The REG Procedure
Model: MODEL1
Test 1 Results for Dependent Variable logTRANS
Source
DF
Mean Square
F Value
Pr > F
Numerator
1
25.07333
162.41
<.0001
Denominator
10
0.15439
Data from Intel Corporation
Increasing power of Intel computer processor chips over years
Plot of residuals
Plot of resid*YEAR. Legend: A = 1 obs, B = 2 obs, etc.
resid |
|
0.6 +
|
|
| A
0.4 + A A
|
|
|
0.2 + A A
|
|
| A
0.0 +------------------------------------------------------------------------A----------------
| A
|
|
-0.2 +
|
| A
| A A
-0.4 +
|
|
|
-0.6 +
|
|
| A
-0.8 +
|
---+-------------+-------------+-------------+-------------+-------------+-------------+--
1970 1975 1980 1985 1990 1995 2000
YEAR
Data from Intel Corporation
Increasing power of Intel computer processor chips over years
Plot of residuals
The UNIVARIATE Procedure
Variable: resid
Moments
N
12
Sum Weights
12
Mean
0
Sum Observations
0
Std Deviation
0.37463418
Variance
0.14035077
Skewness
-0.5243539
Kurtosis
-0.4472994
Uncorrected SS
1.54385842
Corrected SS
1.54385842
Coeff Variation
.
Std Error Mean
0.10814757
Basic Statistical Measures
Location
Variability
Mean
0.000000
Std Deviation
0.37463
Median
0.033830
Variance
0.14035
Mode
.
Range
1.20437
Interquartile Range
0.63072
Tests for Location: Mu0=0
Test
Statistic
p Value
Student's t
t
0
Pr > |t|
1.0000
Sign
M
0
Pr >= |M|
1.0000
Signed Rank
S
3
Pr >= |S|
0.8501
Tests for Normality
Test
Statistic
p Value
Shapiro-Wilk
W
0.939064
Pr < W
0.4860
Kolmogorov-Smirnov
D
0.136633
Pr > D
>0.1500
Cramer-von Mises
W-Sq
0.040599
Pr > W-Sq
>0.2500
Anderson-Darling
A-Sq
0.292949
Pr > A-Sq
>0.2500
Quantiles (Definition 5)
Quantile
Estimate
100% Max
0.4638977
99%
0.4638977
95%
0.4638977
90%
0.4243957
75% Q3
0.3124870
50% Median
0.0338302
25% Q1
-0.3182297
10%
-0.3578260
5%
-0.7404772
1%
-0.7404772
0% Min
-0.7404772
Extreme Observations
Lowest
Highest
Value
Obs
Value
Obs
-0.7404772
11
0.218314
6
-0.3578260
3
0.219373
4
-0.3338563
10
0.405601
7
-0.3026030
2
0.424396
12
-0.0644798
1
0.463898
5
Data from Intel Corporation
Increasing power of Intel computer processor chips over years