180 likes | 292 Views
How to do regression and correlation with. fx-3650. Step 1 Choose REG mode. for linear regression Press the buttons [Mode][Mode][2][1]. Mode. Step 2 Data entry. For entering this dataset clear all data [SHIFT][CLR][1][EXE] data entry 10[,]1003[DT]15[,]1005 [DT]20[,]1010[DT]25[,]
E N D
Step 1 Choose REG mode for linear regression Press the buttons [Mode][Mode][2][1] Mode
Step 2 Data entry For entering this dataset clear all data [SHIFT][CLR][1][EXE] data entry 10[,]1003[DT]15[,]1005 [DT]20[,]1010[DT]25[,] 1011[DT]30[,]1014[DT] SHIFT CLR DT EXE
Step 3 Finding the regression equation For the equation y=A+Bx For A (997.4) Press For B (0.56) Press For regression coeff. (0.966) Press SHIFT x2 S-VAR EXE
Step 3 Finding the correlationcoefficient For the correlationcoefficient r (0.983) Press SHIFT S-VAR EXE
Step 1 Choose REG mode Use Mode 3 (REG) You are offered 3 choices choose linear regression option (1) Press the buttons [Mode][3][1]
Step 2 Data entry For entering this dataset clear all data [SHIFT][Sci][=] data entry 10[,]1003[DT]15[,]1005 [DT]20[,]1010[DT]25[,] 1011[DT]30[,]1014[DT] SHIFT DT Sci
Step 3 Finding the regression equation For the equation y=A+Bx For A (997.4) Press [SHIFT][A][=] For B (0.56) Press [SHIFT][B][=] For regression coeff. (0.966) Press [SHIFT][r][=] SHIFT A B r
Step 1 Choose REG mode Use Mode 3 (REG) You are offered 3 choices choose linear regression option (1) Press the buttons [Mode][3][1]
Step 2 Data entry For entering this dataset clear all data [SHIFT][Sci][=] data entry 10[,]1003[DT]15[,]1005 [DT]20[,]1010[DT]25[,] 1011[DT]30[,]1014[DT] SHIFT DT Sci
r = [x1x2 - (x1 x2)/n] {[x12 – (x1)2/n][x22 – (x2)2/n] Step 3 compute r For x1x2 press [RCL][F] x1 press [RCL][B] x2 press [RCL][E] x12 press [RCL][A] x22 press [RCL][D] you should find r = 0.983
For Old Calculators….fx-3400p or fx-3600 p • Mode: 2 (LR) • Clear data: shift, AC • Enter data x, then XD; Enter data y, then DATA • Check N for entered dataset: Kout, n (3) • y = A + Bx: shift, A (7) = A; shift, B (8) = B; shift, r (9) = r coefficient of correlation
Experimental Design and Statistics 1. Setting questions into statistical questions 2. Setting hypotheses (i.e. expected/theoretical one) 3. Setting statistical null hypotheses 4. Statistical consideration (treatment groups, sample size, replicates, confounding factors, controls etc.) 5. Experimental design 6. Data collection 7. Data analysis
Start here Observations Patterns in space or time Models Explanations or theories Hypothesis Predictions based on model Null Hypothesis Logical opposite to hypothesis Experiment Critical test of null hypothesis Reject Ho Retain Ho Support Refute Interpretation hypothesis hypothesis Don't end here and model and model Generalized scheme of logical components of a research programme (Underwood 1997) Weapon size versus body size as a predictor of winning fights Carcinus maenas Reference: Sneddon et al. 1997, in Behav. Ecol. Sociobiol. 41: 237 - 242